两道新题
This commit is contained in:
@@ -4,7 +4,11 @@
|
||||
"cell_type": "code",
|
||||
"id": "initial_id",
|
||||
"metadata": {
|
||||
"collapsed": true
|
||||
"collapsed": true,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2026-07-05T15:05:59.049967188Z",
|
||||
"start_time": "2026-07-05T15:05:56.833387637Z"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"import os\n",
|
||||
@@ -17,10 +21,15 @@
|
||||
"from tqdm import tqdm"
|
||||
],
|
||||
"outputs": [],
|
||||
"execution_count": null
|
||||
"execution_count": 2
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2026-07-05T15:05:59.150289671Z",
|
||||
"start_time": "2026-07-05T15:05:59.051997256Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"train_df = pd.read_csv('./train.csv')\n",
|
||||
@@ -30,16 +39,136 @@
|
||||
"print(f\"Train: {len(train_df)}, Val: {len(val_df)}, Test: {len(test_df)}\")"
|
||||
],
|
||||
"id": "f32065752f1597fb",
|
||||
"outputs": [],
|
||||
"execution_count": null
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Train: 10908, Val: 1212, Test: 5195\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"execution_count": 3
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2026-07-05T15:05:59.184794043Z",
|
||||
"start_time": "2026-07-05T15:05:59.156968452Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": "train_df.head()",
|
||||
"id": "460c6fffc81814df",
|
||||
"outputs": [],
|
||||
"execution_count": null
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
" id premise \\\n",
|
||||
"9989 6417481c8d यद्यपि हम आज के समय में अल कायदा के साथ केएसएए... \n",
|
||||
"3880 5c5ca34cf6 'Upload him into his body? What body?' \n",
|
||||
"8559 1d3c28ecff yeah and then about every five years you have ... \n",
|
||||
"6316 22e2a4903d θέλω να πω ότι υπήρχε είχα, είχα το ρολόι μου ... \n",
|
||||
"762 307016c21f Yet, in the mouths of the white townsfolk of S... \n",
|
||||
"\n",
|
||||
" hypothesis lang_abv language \\\n",
|
||||
"9989 हर व्यक्ति केएसएम को हमेशा अल कायदा के बराबर म... hi Hindi \n",
|
||||
"3880 I don't think he has a body at all. en English \n",
|
||||
"8559 You have to dig them up every five years, thro... en English \n",
|
||||
"6316 Ήταν ενοχλητικό όταν κάλυψε τα παπούτσια μου. el Greek \n",
|
||||
"762 White townsfolk in Salisbury, N.C. are easily ... en English \n",
|
||||
"\n",
|
||||
" label \n",
|
||||
"9989 2 \n",
|
||||
"3880 1 \n",
|
||||
"8559 1 \n",
|
||||
"6316 1 \n",
|
||||
"762 1 "
|
||||
],
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>id</th>\n",
|
||||
" <th>premise</th>\n",
|
||||
" <th>hypothesis</th>\n",
|
||||
" <th>lang_abv</th>\n",
|
||||
" <th>language</th>\n",
|
||||
" <th>label</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>9989</th>\n",
|
||||
" <td>6417481c8d</td>\n",
|
||||
" <td>यद्यपि हम आज के समय में अल कायदा के साथ केएसएए...</td>\n",
|
||||
" <td>हर व्यक्ति केएसएम को हमेशा अल कायदा के बराबर म...</td>\n",
|
||||
" <td>hi</td>\n",
|
||||
" <td>Hindi</td>\n",
|
||||
" <td>2</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3880</th>\n",
|
||||
" <td>5c5ca34cf6</td>\n",
|
||||
" <td>'Upload him into his body? What body?'</td>\n",
|
||||
" <td>I don't think he has a body at all.</td>\n",
|
||||
" <td>en</td>\n",
|
||||
" <td>English</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>8559</th>\n",
|
||||
" <td>1d3c28ecff</td>\n",
|
||||
" <td>yeah and then about every five years you have ...</td>\n",
|
||||
" <td>You have to dig them up every five years, thro...</td>\n",
|
||||
" <td>en</td>\n",
|
||||
" <td>English</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6316</th>\n",
|
||||
" <td>22e2a4903d</td>\n",
|
||||
" <td>θέλω να πω ότι υπήρχε είχα, είχα το ρολόι μου ...</td>\n",
|
||||
" <td>Ήταν ενοχλητικό όταν κάλυψε τα παπούτσια μου.</td>\n",
|
||||
" <td>el</td>\n",
|
||||
" <td>Greek</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>762</th>\n",
|
||||
" <td>307016c21f</td>\n",
|
||||
" <td>Yet, in the mouths of the white townsfolk of S...</td>\n",
|
||||
" <td>White townsfolk in Salisbury, N.C. are easily ...</td>\n",
|
||||
" <td>en</td>\n",
|
||||
" <td>English</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"execution_count": 4
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
|
||||
Reference in New Issue
Block a user